Image segmentation with superpixel-based covariance descriptors in low-rank representation

2016/05/18 by Xianbin Gu, Gu, Xianbin, Jeremiah D. Deng +3
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Medical Image Segmentation Techniques #Remote-Sensing Image Classification #Sparse and Compressive Sensing Techniques

paper · pdf · doi:10.48550/arxiv.1605.05466

openalex publication_date 2016/05/18 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28

Abstract

This paper investigates the problem of image segmentation using superpixels. We propose two approaches to enhance the discriminative ability of the superpixel's covariance descriptors. In the first one, we employ the Log-Euclidean distance as the metric on the covariance manifolds, and then use the RBF kernel to measure the similarities between covariance descriptors. The second method is focused on extracting the subspace structure of the set of covariance descriptors by extending a low rank representation algorithm on to the covariance manifolds. Experiments are carried out with the Berkly Segmentation Dataset, and compared with the state-of-the-art segmentation algorithms, both methods are competitive.

Citations

• Tensor Decompositions and Applications
• Robust principal component analysis?

Related

• More About Covariance Descriptors for Image Set Coding: Log-Euclidean Framework based Kernel Matrix Representation
• Generating superpixels using deep image representations
• Combining Multi-level Contexts of Superpixel using Convolutional Neural Networks to perform Natural Scene Labeling
• Superpixel Segmentation Based on Spatially Constrained Subspace Clustering
• Covapixels